List your company

Mathematical Reasoning on MATH500 (Acc, TF, Acc/TF)

83.8AccASC
39.70451.15262.674.048Jan 6, 2026

Evaluation results

MethodLinks
ASCModel=GEMMA-3-27B2026.0183.8121.290.69
ReASC (offline)Model=GEMMA-3-27B2026.0183.6101.320.83
ReASC (online)Model=GEMMA-3-27B2026.0183.6100.620.83
SCModel=GEMMA-3-27B, k=162026.0182.6291.360.28
ESCModel=GEMMA-3-27B, w=42026.0182.6126.560.65
ReASC (offline)Model=QWEN-2.5-7B2026.0181.229.262.78
ReASC (online)Model=QWEN-2.5-7B2026.0181.230.742.64
ASCModel=QWEN-2.5-7B2026.0180.837.252.17
SCModel=QWEN-2.5-7B, k=162026.0180.671.591.13
ESCModel=QWEN-2.5-7B, w=42026.0180.639.712.03
pass@1Model=GEMMA-3-27B2026.0177.6——
SCModel=QWEN-2.5-3B, k=162026.0172.631.762.29
ESCModel=QWEN-2.5-3B, w=42026.0172.621.753.34
ASCModel=QWEN-2.5-3B2026.0172.620.843.48
ReASC (online)Model=QWEN-2.5-3B2026.0172.217.724.07
ReASC (offline)Model=QWEN-2.5-3B2026.0171.816.84.27
SCModel=GEMMA-3-4B, k=162026.0171.650.151.43
ESCModel=GEMMA-3-4B, w=42026.0171.630.482.35
ASCModel=GEMMA-3-4B2026.0171.628.682.5
ReASC (offline)Model=GEMMA-3-4B2026.0171.425.592.79
ReASC (online)Model=GEMMA-3-4B2026.0171.426.172.73
pass@1Model=QWEN-2.5-7B2026.0171.2——
pass@1Model=GEMMA-3-4B2026.0163.2——
pass@1Model=QWEN-2.5-3B2026.0161.8——
ASCModel=LLAMA-3.2-3B2026.015520.132.73
ReASC (offline)Model=LLAMA-3.2-3B2026.015518.273.01
SCModel=LLAMA-3.2-3B, k=162026.0154.825.312.17
ESCModel=LLAMA-3.2-3B, w=42026.0154.821.412.56
ReASC (online)Model=LLAMA-3.2-3B2026.0153.416.753.19
pass@1Model=LLAMA-3.2-3B2026.0141.4——